© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Joseph Bloom · Initial Gemma-2B SAEs
    3. Gemma-2B
    4. Residual Stream
    5. 10-RES-JB
    6. 618
    Prev
    Next
    INDEX
    Explanations

    references to player transactions in sports contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-Residual-Stream-SAEs/gemma_2b_blocks.10.hook_resid_post_16384
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    chanind/openwebtext-gemma
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    standard
    Context Size
    1,024
    Dataset
    ctigges/openwebtext-gemma-1024-cl
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    50
    +0.29
    1.1%
    1150
    +0.13
    0.5%
    1042
    +0.13
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1445
    +0.29
    0.08
    1150
    +0.13
    0.03
    1042
    +0.13
    0.04
    Negative Logits
    <bos>
    -1.67
     swarovski
    -0.96
     anhyd
    -0.87
     tricot
    -0.84
    ⓧ
    -0.79
    /***
    
    -0.78
     fluo
    -0.76
     oleo
    -0.75
     embodi
    -0.75
     /**
    
    -0.72
    POSITIVE LOGITS
     panik
    0.99
     maksi
    0.99
     kosme
    0.89
     seksi
    0.87
     praktik
    0.87
     minimalis
    0.86
     kriminal
    0.86
     kooper
    0.85
     indik
    0.83
     protokol
    0.82
    Activations Density 0.556%

    No Known Activations